Essentials Of Computer Organization And Architecture 5th Edition Linda Null, Julia Lobur - Solutions

A certain microprocessor requires either 2, 3, 4, 8, or 12 machine cycles to perform various operations. A total of 25% of its instructions require 2 machine cycles, 20% require 3 machine cycles, 17.5% require 4 machine cycles, 12.5% require 8 machine cycles, and 25% require 12 machine cycles.1.
In our discussion of the SSTF disk scheduling algorithm, we stated that the problem of starvation “is at its worst with low disk utilization rates.” Explain why this is so.
Repeat Exercise 21 for the following disk tracks (assuming the read/write head is at track 50, moving outward):48, 14, 85, 35, 84, 61, 30, 22
On a particular brand of disk drive, the time that it takes for the disk arm to pass over a single disk track without stopping is 500ns. However, once the head reaches the track for which it has a service request, it needs 2ms to “settle” over the required track before it can start reading or
Repeat the previous problem using the following tracks:82, 97, 35, 75, 53, 47, 17, 11
Calculate the number of disk tracks traversed using the FCFS, SSTF, SCAN, and LOOK algorithms for the series of disk track service requests given below. At the time the first request arrives in the disk request queue, the read/write head is at track 50, moving toward the outer (lower-numbered)
In our discussion of the physical aspects of disk performance, we stated that replacing 7,200rpm disks with 10,000rpm disks can bring a 10% to 50% performance improvement. Why would an improvement of only 10% occur? Could it be that no improvement at all would occur? Explain. (Hint: Rotational
The sidebar in Section 11.5.2 presents ways in which program performance can be improved. For each of the tips in the sidebar, state whether a computer organization and architecture issue is involved. If so, explain the reasoning behind the advice as given. If you feel anything is missing from the
We mentioned that a large volume of data is gathered during system probe traces. To give you some idea of the actual volume of data involved, suppose plans are being made to install a hardware probe that reports the contents of a system’s program counter, instruction register, accumulator, memory
SPEC and the TPC both publish benchmarks for web server systems. Visit the respective websites of these organizations(www.spec.org and www.tpc.org) to try to find identical (or comparable) systems that have results posted on both sites. Discuss your findings.
We discussed the limitations of the harmonic mean in its application to computer performance assessment. A number of critics have suggested that the SPEC should use the harmonic mean instead. Suggest a unit of “work” that would be appropriate for reformulating the SPEC benchmarks as rate
Suppose you have just been assigned to a committee that has been tasked with purchasing a new enterprise file server that will support customer account activity as well as many administrative functions, such as producing a weekly payroll. (Yes, a committee frequently makes these decisions!) One of
Suppose a friend has asked you to help him make a choice as to what kind of computer he should buy for his personal use at home. What would you look for in comparing various makes and models? How is your line of thinking different in this situation than if you were to help your employer purchase a
Which of the benchmarks discussed in this chapter would be most helpful to you if you were about to purchase a system to be used in DNA research? Why would you choose this one? Would any of the other benchmarks be of interest to you? Why or why not?
Besides the retail business sector, what other organizations would need good performance from a transaction-processing system? Justify your answer.
What value do you think there would be in comparing the results of two different SPEC CPU releases, say, SPEC95 and SPEC2000?
Suppose that you are looking into purchasing a new computer system. You have suitable benchmark results for all of the systems that you are considering, except for System X, Model Q. The benchmark results have been reported for System X, Model S, and they are not quite as good as that of several
What would you say to a vendor who tells you that his system runs 50% of the SPEC benchmark kernel programs twice as fast as the leading competitive system? Which statistical fallacy is at work here?
What are the limitations of synthetic benchmarks such as Whetstone and Dhrystone? Do you think the concept of a synthetic benchmark could be extended to overcome these limitations?Explain your answer.
With regard to the performance data cited for programs v, w, x, y, and z in Section 11.3, find the geometric means of the runtimes of the programs for System B and System C, using System A as the reference system. Verify that the ratios of the means are consistent with the results obtained using
Table 11.2 shows an execution mix and runtimes for two computers, System A and System C. In this example, System C is 83% faster than System A. Table 11.3 shows runtimes for System A with a different execution mix. Using the execution mix in Table 11.3, calculate the percentage by which System C
Explain the challenges of embedded software development.How do designers answer these challenges?
In an ideal embedded operating system, would all nonkernel threads always execute at lower priority than interrupts?
Explain interrupt latency. How is it related to context switch time?
We say that in embedded operating systems, if the highestpriority user thread is executing when a high-priority interrupt occurs, most operating systems will continue to process the user thread and keep the interrupt in queue until processing is completed. Under what circumstances would this be and
Present arguments for and against the use of dynamic memory in embedded systems. Should it be banned for use under all circumstances? Why or why not?
Provide a detailed logic diagram for a multiplexer that could be used in an FPGA.
In the sidebar concerning watchdog timer engineering decisions, we stated that rebooting an embedded system typically takes less time than rebooting a personal computer. Why do you think this is so?
What happens if an infinite loop includes a watchdog timer reset? Name one thing that can be done to guard against this.
Research quantum computing and provide a summary of a recent article on the topic.
With respect to Flynn’s taxonomy, where do systolic arrays fit?What about clusters of workstations?
Explain the differences between SIMD and systolic array computing when the systolic array is one-dimensional.
These two questions deal with a single perceptron of a neural network.1.a) The logical NOT is a little trickier than AND or OR, but can be done. In this case, there is only one Boolean input.What would the weight and threshold be for this perceptron to recognize the logical NOT operator?2.b) Show
Describe the process of supervised learning in neural networks from a mathematical perspective.
Compare and contrast supervised learning and unsupervised learning with regard to neural networks.
Do neural networks process information sequentially?Explain.
Should the memory of a dataflow system be associative or address based? Explain.
Describe write-through and write-back cache modification as they are used in shared memory systems, and the advantages and disadvantages of both approaches.
What are the main problems with using crossbars for interconnection networks? What problems do buses present in interconnection networks?
What is the difference between UMA and NUMA?
Why are distributed systems desirable?
Compare and contrast the superscalar architecture to the VLIW architecture.
Which model, VLIW or superscalar, presents the greater challenge for compilers? Why?
Describe briefly and compare the VLIW and superscalar models with respect to instruction-level parallelism.
For what type of program-level parallelism (data or control) is SIMD best suited? For what type of program-level parallelism is MIMD best suited?
What is the difference between SIMD and SPMD?
How are SIMD and MIMD similar? How are they different?Note: You are not to define the terms, but instead compare the models.
Describe the characteristics of MIMD multiprocessors that distinguish them from multicomputer systems or computer networks.
Explain the difference between loosely coupled and tightly coupled architectures.
. Flynn’s taxonomy consists of four primary models of computation. Briefly describe each of the categories and give an example of a high-level problem for which each of these models might be used.
In Flynn’s taxonomy:1. ◆a) What does SIMD stand for? Give a brief description and an example.2.b) What does MIMD stand for? Give a brief description and an example.
Suppose that a RISC machine uses five register windows.1.a) How deep can the procedure calls go before registers must be saved in memory? (That is, what is the maximum number of “active” procedure calls that can be made before we need to save any registers in memory?)2.b) Suppose two more calls
Recall our discussions from Chapter 8 regarding context switches. These occur when one process stops using the CPU and another process begins. In this sense, register windows could be viewed as a potential weakness of RISC. Explain why this is the case.
Suppose a RISC machine uses overlapping register windows for passing parameters between procedures. The machine has 298 registers. Each register window has 32 registers, of which 10 are global variables and 10 are local variables. Answer the following:1.a) How many registers would be available for
A RISC processor has 186 total registers, with 18 globals.There are 12 register windows, each with 10 locals. How many input/output registers are in each register window?
A RISC processor has 152 total registers, with 12 designated as global registers. The 10 register windows each have 6 input registers and 6 output registers. How many local registers are in each register window set?
A RISC processor has 8 global registers and 10 register windows. Each window has 4 input registers, 8 local registers, and 4 output registers. How many total registers are in this CPU? (Hint:Remember, because of the circular nature of the windows, the output registers of the last window are shared
Suppose a RISC machine uses overlapping register windows with:1. 10 global registers 2. 6 input parameter registers 3. 10 local registers 4. 6 output parameter registers How large is each overlapping register window?
3. What does the “reduced” in reduced instruction set computer really mean?
2. Which characteristics of RISC systems could be directly implemented in CISC systems? Which characteristics of RISC machines could not be implemented in CISC machines (based on the defining characteristics of both architectures as listed in Table 9.1)?
1. Why do RISC machines operate on registers?
Research various command-line interfaces (such as UNIX, MS-DOS, and VMS) and different windows interfaces (such as any Microsoft Windows product, MacOS, and KDE).1.a) Consider some of the major commands, such as getting a directory listing, deleting a file, or changing directories.Explain how each
We said that the risk of deadlock is always present anytime a system resource is locked. Describe a way in which deadlock can occur.
23. To improve performance, your company has decided to replicate its product database across several servers so that not all transactions go through a single system. What sorts of issues will need to be considered?
22. In what ways are n-tiered transaction processing architectures superior to single-tiered architectures? Which usually costs more?
21. Answer the following with respect to database processing:1.a) What is a race condition? Give an example.2.b) How can race conditions be prevented?3.c) What are the risks in race condition prevention?
19. Java is called an interpreted language, yet Java is a compiled language that produces a binary output stream. Explain how this language can be both compiled and interpreted.20. 20. We stated that the performance of a Java program running in the JVM cannot possibly match that of a regular
18. The Java bytecode for access to the local variable array for a class is at most two bytes long. One byte is used for the opcode; the other indicates the offset into the array. How many variables can be held in the local variable array? What do you think happens when this number is exceeded?
17. We stated that only one method at a time can be active within each thread running in the JVM. Why do you think this is the case?
16. Why do you suppose the method area of a JVM is global to all of the threads running in the virtual machine environment?
15. Why is the execution environment of a Java class called a virtual machine? How does this virtual machine compare to a real machine running code written in C?
14. Discuss the following questions relative to compilers:1.a) Which phase of a compiler would give you a syntax error?2.b) Which phase complains about undefined variables?3.c) If you try to add an integer to a character string, which compiler phase would emit the error message?
13. 13. What are the advantages of using a compiled language over an interpreted one? Under what circumstances would you choose to use an interpreted language?
12. 12. Under what circumstances would you argue in favor of using assembly language code for developing an application program?
11. 11. Why should assembly language be avoided for general application development? Under what circumstances is assembly language preferred or required?
10. 10. What problems does an assembler have to overcome in order to produce complete binary code in one pass over the source file?How would code written for a one-pass assembler be different from code written for a two-pass assembler?
9. ◆9. Discuss the advantages and disadvantages of dynamic linking.
8. 8. Suppose there were no such thing as relocatable program code. How would the process of memory paging be made more complex?
7. ◆7. When is it appropriate to use nonrelocatable binary program code? Why is relocatable code preferred?
6. 6. What advantages would there be to using both subsystems and logical partitions on the same machine?
5. ◆5. Under what circumstances is it desirable to collect groups of processes and programs into subsystems running on a large computer? What advantages would there be to creating logical partitions on this system?
4. 4. What is the difference between multiprogramming and multiprocessing? Between multiprogramming and multithreading?
3. 3. If you were writing code for a real-time operating system, what restrictions might you want to impose on the system? Hint: Think about the types of things that cause unpredictable reaction times.(How might a memory access be delayed, for example?)
2. 2. Microkernels attempt to provide as small a kernel as possible, putting much of the operating system support into additional modules. What do you feel are the minimum services that the kernel must provide?
1. 1. What do you feel are the limitations of a computer that has no operating system? How would a user load and execute a program?
49. Our discussion of RAID is biased toward consideration of standard rotating magnetic disks. Is RAID necessary for SSD storage? If not, does this make SSD storage slightly more affordable for the enterprise? If it is necessary, do the redundant disks necessarily also need to be SSD?
48.a) Which of the RAID systems described in this chapter cannot tolerate a single disk failure?1.b) Which can tolerate more than one simultaneous disk failure?
47. A particular high-performance computer system has been functioning as an e-business server on the Web. This system supports $10,000 per hour in gross business volume. It has been estimated that the net profit per hour is $1,200. In other words, if the system goes down, the company will lose
46. Suppose you have a 100GB database housed on a disk array that supports a transfer rate of 60MBps and a tape drive that supports 200GB cartridges with a transfer rate of 80MBps. How long will it take to back up the database? What is the transfer time if 2:1 compression is possible?
45. Discuss the pros and cons of using disk versus tape for backups.
44. You have a need to archive a large amount of data. You are trying to decide whether to use tape or optical storage methods.What are the characteristics of this data and how it is used that will influence your decision?
43. How would the error-correction requirements of an optical document storage system differ from the error-correction requirements of the same information stored in textual form? What are the advantages offered by having different levels of error correction for optical storage devices?
42. Discuss the difference between how DLT and DAT record data. Why would you say that one is better than the other?
41. A company that has engaged in a business that requires fast response times has just received a bid for a new system that includes much more storage than was specified in the requirements document. When the company questioned the vendor about the increased storage, the vendor said he was bidding
40. The disk drives connected to the servers in your company’s server farm are nearing the end of their useful lives. Management is considering replacing 8TB of disk capacity with SSDs. Someone is making the argument that the difference in the cost between the SSDs and traditional magnetic disks
38. Compare the disk specifications for the HDD and SSD in Figures 7.15 and 7.17, respectively. Which items are the same?Why? Which items are different? Why?
37. 37. Explain wear leveling and why it is needed for SSDs. We said that wearleveling is important for the continual updating of virtual memory pagefiles. What problem does wearleveling aggravate for pagefiles?
36. 36. In Section 7.6.2, we said that magnetic disks are power hungry as compared to main memory. Why do you think this is the case?
35. How does the organization of an SSD differ from a magnetic disk? How are they similar to a disk?
4. How does the organization of an optical disk differ from the organization of a magnetic disk?

Showing 200 - 300 of 1321

Essentials Of Computer Organization And Architecture 5th Edition Linda Null, Julia Lobur - Solutions

Step by Step Answers